llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Ling-3.0-tiny-IQ4_XS:latest
OLLAMA GGUFbailingmoe3 · 7.9B · IQ4_XS
Aug 30, 2026 · Intel Core™ i7-7700HQ
Global Score
74 vs 87
Hardware Fit
99 vs 100
Quality Score
63 vs 82
Hardware
llama3.2:3b Ling-3.0-tiny-IQ4_…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUSTeK COMPUTER INC. GL702VMK
CPUCortex-A78AEIntel Core™ i7-7700HQ
Cores68
RAM7 GB16 GB
GPUIntegrated / UnknownNVIDIA GeForce GTX 1060
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
llama3.2:3b Ling-3.0-tiny-IQ4_…
Tokens/sec21.124.7
First chunk1032 ms283 ms
TTFT1.0 s283 ms
Load time8.4 s45.8 s
Memory usage2.4 GB4.3 GB
Memory %32%27%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
Ling-3.0-tiny-IQ4_XS:la…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
llama3.2:3b
Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
Ling-3.0-tiny-IQ4_XS:la…
Reasoning
17/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
9/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest